A note on estimation of states in HMM with unknown parameters
暂无分享,去创建一个
Summary Estimation of states in HMM(Hidden Markov Model) with unknown parameters is very important topic in many fields. In this paper we propose an optimal estimation method which minimizes an error rate with reference to the Bayes criterion. We also propose approximate method in order to reduce computational complexity.
[1] J. Berger. Statistical Decision Theory and Bayesian Analysis , 1988 .
[2] Masaaki Nagata,et al. A Stochastic Japanese Morphological Analyzer Using a Forward-DP Backward-A* N-Best Search Algorithm , 1994, COLING.
[3] Shu Lin,et al. Error Control Coding , 2004 .